© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21850
    Prev
    Next
    INDEX
    Explanations

    VA healthcare clinic forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    塾
    -0.09
    éĿ¢è²Į
    -0.09
     ка
    -0.09
    髦
    -0.08
    erno
    -0.08
    æīĴ
    -0.08
    ç¥ľ
    -0.08
    ä¼ĬåĪ©
    -0.08
    .aws
    -0.08
     Gee
    -0.08
    POSITIVE LOGITS
    zt
    0.09
     SharePoint
    0.09
    æ´½
    0.09
    æĬļ
    0.09
    thé
    0.09
    chter
    0.09
    ëĦ¤
    0.09
    ä¹ħ
    0.09
    adt
    0.08
     Tatto
    0.08
    Activations Density 0.077%

    No Known Activations